Machine vision system and method for inspection, homing, guidance and docking with respect to remote objects

• US 6,362,875 B1
• Filed: 12/10/1999
• Issued: 03/26/2002
• Est. Priority Date: 12/10/1999
• Status: Expired due to Fees

• Current Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Original Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Inventors: Burkley, Rodger E.
• Primary Examiner(s): Buczinski, Stephen C.
• Application Number:
  US09/458,908
• Time in Patent Office: 837 Days
• Field of Search: 356/139.03, 382/106, 382/103, 382/153, 702/153, 348/169
• US Class Current: 356/139.03
• CPC Class Codes: B63G 2008/008 Docking stations for unmanned underwater vessels, or the like
• CPC Class Codes: G01S 5/163 Determination of attitude using inertial means G01C9/00; control of attitude G05D1/49
• CPC Class Codes: G05D 1/0225 involving docking at a fixed facility, e.g. base station or loading bay parking aids B62D15/027
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06V 10/42 Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation

Abstract

A system and method for homing, docking and tracking of one object with respect to another provides a camera for acquring images and a machine vision processor inter-connected with the camera. The machine vision processor includes a sacale-invariant and rotation-invariant pattern recognition application that retrieves stored images representative of the object being viewed that includes data representative of a fiducial within the object image. The stored image and its fiducial are compared to the acquired image. The image is aligned within the processor based upon a detected fiducial and the relative orientation and position of the object is determined based upon the acquired image. Data representative of the relative position and orientation is used to manipulate one of the objects so as to bring at least one of the objects to a predetermined position with respect to the other of the objects. The predetermined position can be a docked position or a following, on-station position, among others.

Claims

1. A system for tracking and guiding the position of a first object with respect to a second object comprising:

a camera assembly located with respect to the first object;

a machine vision processor in communication with the camera assembly constructed and arranged to acquire an image of the second object and to locate a fiducial within the acquired image;

an image storage bank in communication with the machine vision processor, including a predetermined stored image data representative of the second object and the fiducial;

means, within the machine vision processor, for comparing the stored image data with the acquired image and for determining relative distance and orientation of the acquired image with respect to a known distance and orientation of the stored image data;

a translator, responsive to the means for comparing and determining, that generates position data for the first object with respect to the second object; and

means for transmitting the position data from the first object to the second object to aid guiding the position of the second object with respect to said first object.

2. The system as set forth in claim 1 further comprising a controller, operatively connected to the translator, for controlling positioning of the first object with respect to the second object in response to data provided by the translator.

3. The system as set forth in claim 2, wherein the machine vision processor includes a computer readable medium executing program instructions thereon for performing scale-invariant and rotation-invariant pattern recognition with respect to the acquired image.

4. The system as set forth in claim 3 wherein each of the first object and the second object include a respective first docking unit and second docking unit and wherein the controller is constructed and arranged to move the first docking unit with respect to the second docking unit to thereby align and engage the first docking unit with respect to the second docking unit.

5. The system as set forth in claim 4 wherein at least one of the first docking unit and the second docking unit comprise an elongated member.

6. The system as set forth in claim 5 wherein the first docking unit includes a movement controller that causes the first docking unit to move within a predetermined range of movement.

7. The system as set forth in claim 3 wherein the machine vision processor further includes an aligner that, based upon a location of the fiducial in the acquired image determines an alignment of the acquired image with respect to the stored image data.

8. The system as set forth in claim 7 wherein the fiducial comprises at least one localized structure on the second object within a field of view of the camera.

9. A method for tracking and guiding the position of a first object with respect to a second object comprising:

acquiring, with a machine vision processor in communication with a camera assembly, an image of the second object and locating a fiducial within the acquired image;

retrieving stored image data from an storage bank in communication with the machine vision processor, the stored image data being representative of the second object and the fiducial;

comparing, using the machine vision processor, the stored image data with the acquired image and determining relative distance and orientation of the acquired image with respect to a known distance and orientation of the stored image data;

generating, based upon the determining step, position data for the first object with respect to the second; and

transmitting the position data from the first object to the second object to aid guiding the position of the second object with respect to the first object.

10. The method as set forth in claim 9 further comprising controlling, in response to the generating step, positioning of the first object with respect to the second object.

11. The method as set forth in claim 10, wherein the step of comparing and the step of determining includes executing program instructions of a computer readable medium that performs scale-invariant and rotation-invariant pattern recognition with respect to the acquired image.

12. The method as set forth in claim 11 wherein each of the first object and the second object include a respective first docking unit and second docking unit and wherein the step of positioning includes moving the first docking unit with respect to the second docking unit to thereby align and engage the first docking unit with respect to the second docking unit.

13. The method as set forth in claim 12 further comprising defining the first docking unit as an elongated member.

14. The method as set forth in claim 13 wherein the step of positioning includes moving the first docking unit within a predetermined range of movement.

15. The method as set forth in claim 11 further comprising aligning, based upon a location of the fiducial in the acquired image, the acquired image with respect to the stored image data.

16. The system as set forth in claim 15 wherein the step of aligning includes identifying at least one localized structure on the second object within a field of view of the camera and recognizing the localized structure as the fiducial.